ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Communicative speech synthesis using constituent word attributes

Yoko Greenberg, Minoru Tsuzaki, Hiroaki Kato, Yoshinori Sagisaka

Aiming at F0 control for communicative speech synthesis, the relationship between word attributes and F0 characteristics was analyzed. By analyzing one-phrase utterances in conversational situations, we studied correlations between word attributes defined by their impressions and prosodic control characteristics. For word attribute description, we used three dimensions in perceptual impressions, confident-doubtful, allowable-unacceptable and positive-negative obtained from our previous studies on one syllable utterances of "n". The result showed that F0 height, F0 dynamic patterns and duration could be consistently controlled by the word attributes. The positive-(negative) can be controlled by F0 height, while confident-doubtful, allowable-unacceptable were reflected in F0 dynamic patterns and duration. These results confirmed the usefulness of word attributes in communicative speech synthesis.

doi: 10.21437/Interspeech.2005-330

Cite as: Greenberg, Y., Tsuzaki, M., Kato, H., Sagisaka, Y. (2005) Communicative speech synthesis using constituent word attributes. Proc. Interspeech 2005, 517-520, doi: 10.21437/Interspeech.2005-330

  author={Yoko Greenberg and Minoru Tsuzaki and Hiroaki Kato and Yoshinori Sagisaka},
  title={{Communicative speech synthesis using constituent word attributes}},
  booktitle={Proc. Interspeech 2005},